Training in progress, step 2140, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb7f19d9d893cf36d7b2eee85b092d4267e76bc352c4514f1139d915d70a7ba5
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca1bb3d30767fe7e0d79dbecb1963b8c072075cfe3b9f7dcfcdbfec5813221db
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:326cb78aefd0e9b98ec021e9d4492162a002a65533090a9f2b313d5caa6eff83
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:784b3afeac39402d612e3fef4cca4d417c24e4162e6bce679de064562b378d60
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2148,6 +2148,16 @@
|
|
| 2148 |
"mean_token_accuracy": 0.7499327704310417,
|
| 2149 |
"num_tokens": 9873482.0,
|
| 2150 |
"step": 2130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2151 |
}
|
| 2152 |
],
|
| 2153 |
"logging_steps": 10,
|
|
@@ -2167,7 +2177,7 @@
|
|
| 2167 |
"attributes": {}
|
| 2168 |
}
|
| 2169 |
},
|
| 2170 |
-
"total_flos": 4.
|
| 2171 |
"train_batch_size": 4,
|
| 2172 |
"trial_name": null,
|
| 2173 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.45653333333333335,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2148 |
"mean_token_accuracy": 0.7499327704310417,
|
| 2149 |
"num_tokens": 9873482.0,
|
| 2150 |
"step": 2130
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"entropy": 0.9601933643221855,
|
| 2154 |
+
"epoch": 0.45653333333333335,
|
| 2155 |
+
"grad_norm": 0.249656543135643,
|
| 2156 |
+
"learning_rate": 9.020736517755733e-05,
|
| 2157 |
+
"loss": 1.0663026809692382,
|
| 2158 |
+
"mean_token_accuracy": 0.7673163414001465,
|
| 2159 |
+
"num_tokens": 9924229.0,
|
| 2160 |
+
"step": 2140
|
| 2161 |
}
|
| 2162 |
],
|
| 2163 |
"logging_steps": 10,
|
|
|
|
| 2177 |
"attributes": {}
|
| 2178 |
}
|
| 2179 |
},
|
| 2180 |
+
"total_flos": 4.708127325085594e+16,
|
| 2181 |
"train_batch_size": 4,
|
| 2182 |
"trial_name": null,
|
| 2183 |
"trial_params": null
|